linux-stable/kernel/sched/clock.c

483 lines
12 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* sched_clock() for unstable CPU clocks
*
* Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra
*
2008-07-09 04:15:33 +00:00
* Updates and enhancements:
* Copyright (C) 2008 Red Hat, Inc. Steven Rostedt <srostedt@redhat.com>
*
* Based on code by:
* Ingo Molnar <mingo@redhat.com>
* Guillaume Chazarain <guichaz@gmail.com>
*
*
* What this file implements:
*
* cpu_clock(i) provides a fast (execution time) high resolution
* clock with bounded drift between CPUs. The value of cpu_clock(i)
* is monotonic for constant i. The timestamp returned is in nanoseconds.
*
* ######################### BIG FAT WARNING ##########################
* # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can #
* # go backwards !! #
* ####################################################################
*
* There is no strict promise about the base, although it tends to start
* at 0 on boot (but people really shouldn't rely on that).
*
* cpu_clock(i) -- can be used from any context, including NMI.
* local_clock() -- is cpu_clock() on the current CPU.
*
* sched_clock_cpu(i)
*
* How it is implemented:
*
* The implementation either uses sched_clock() when
* !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK, which means in that case the
* sched_clock() is assumed to provide these properties (mostly it means
* the architecture provides a globally synchronized highres time source).
*
* Otherwise it tries to create a semi stable clock from a mixture of other
* clocks, including:
*
* - GTOD (clock monotomic)
* - sched_clock()
* - explicit idle events
*
* We use GTOD as base and use sched_clock() deltas to improve resolution. The
* deltas are filtered to provide monotonicity and keeping it within an
* expected window.
*
* Furthermore, explicit sleep and wakeup hooks allow us to account for time
* that is otherwise invisible (TSC gets stopped).
*
*/
#include "sched.h"
#include <linux/sched_clock.h>
/*
* Scheduler clock - returns current time in nanosec units.
* This is default implementation.
* Architectures and sub-architectures can override this.
*/
unsigned long long __weak sched_clock(void)
{
return (unsigned long long)(jiffies - INITIAL_JIFFIES)
* (NSEC_PER_SEC / HZ);
}
EXPORT_SYMBOL_GPL(sched_clock);
static DEFINE_STATIC_KEY_FALSE(sched_clock_running);
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
/*
* We must start with !__sched_clock_stable because the unstable -> stable
* transition is accurate, while the stable -> unstable transition is not.
*
* Similarly we start with __sched_clock_stable_early, thereby assuming we
* will become stable, such that there's only a single 1 -> 0 transition.
*/
static DEFINE_STATIC_KEY_FALSE(__sched_clock_stable);
static int __sched_clock_stable_early = 1;
sched/clock: Provide better clock continuity When switching between the unstable and stable variants it is currently possible that clock discontinuities occur. And while these will mostly be 'small', attempt to do better. As observed on my IVB-EP, the sched_clock() is ~1.5s ahead of the ktime_get_ns() based timeline at the point of switchover (sched_clock_init_late()) after SMP bringup. Equally, when the TSC is later found to be unstable -- typically because SMM tries to hide its SMI latencies by mucking with the TSC -- we want to avoid large jumps. Since the clocksource watchdog reports the issue after the fact we cannot exactly fix up time, but since SMI latencies are typically small (~10ns range), the discontinuity is mainly due to drift between sched_clock() and ktime_get_ns() (which on my desktop is ~79s over 24days). I dislike this patch because it adds overhead to the good case in favour of dealing with badness. But given the widespread failure of TSC stability this is worth it. Note that in case the TSC makes drastic jumps after SMP bringup we're still hosed. There's just not much we can do in that case without stupid overhead. If we were to somehow expose tsc_clocksource_reliable (which is hard because this code is also used on ia64 and parisc) we could avoid some of the newly introduced overhead. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-12-15 12:36:17 +00:00
/*
* We want: ktime_get_ns() + __gtod_offset == sched_clock() + __sched_clock_offset
sched/clock: Provide better clock continuity When switching between the unstable and stable variants it is currently possible that clock discontinuities occur. And while these will mostly be 'small', attempt to do better. As observed on my IVB-EP, the sched_clock() is ~1.5s ahead of the ktime_get_ns() based timeline at the point of switchover (sched_clock_init_late()) after SMP bringup. Equally, when the TSC is later found to be unstable -- typically because SMM tries to hide its SMI latencies by mucking with the TSC -- we want to avoid large jumps. Since the clocksource watchdog reports the issue after the fact we cannot exactly fix up time, but since SMI latencies are typically small (~10ns range), the discontinuity is mainly due to drift between sched_clock() and ktime_get_ns() (which on my desktop is ~79s over 24days). I dislike this patch because it adds overhead to the good case in favour of dealing with badness. But given the widespread failure of TSC stability this is worth it. Note that in case the TSC makes drastic jumps after SMP bringup we're still hosed. There's just not much we can do in that case without stupid overhead. If we were to somehow expose tsc_clocksource_reliable (which is hard because this code is also used on ia64 and parisc) we could avoid some of the newly introduced overhead. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-12-15 12:36:17 +00:00
*/
__read_mostly u64 __sched_clock_offset;
static __read_mostly u64 __gtod_offset;
sched/clock: Provide better clock continuity When switching between the unstable and stable variants it is currently possible that clock discontinuities occur. And while these will mostly be 'small', attempt to do better. As observed on my IVB-EP, the sched_clock() is ~1.5s ahead of the ktime_get_ns() based timeline at the point of switchover (sched_clock_init_late()) after SMP bringup. Equally, when the TSC is later found to be unstable -- typically because SMM tries to hide its SMI latencies by mucking with the TSC -- we want to avoid large jumps. Since the clocksource watchdog reports the issue after the fact we cannot exactly fix up time, but since SMI latencies are typically small (~10ns range), the discontinuity is mainly due to drift between sched_clock() and ktime_get_ns() (which on my desktop is ~79s over 24days). I dislike this patch because it adds overhead to the good case in favour of dealing with badness. But given the widespread failure of TSC stability this is worth it. Note that in case the TSC makes drastic jumps after SMP bringup we're still hosed. There's just not much we can do in that case without stupid overhead. If we were to somehow expose tsc_clocksource_reliable (which is hard because this code is also used on ia64 and parisc) we could avoid some of the newly introduced overhead. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-12-15 12:36:17 +00:00
struct sched_clock_data {
u64 tick_raw;
u64 tick_gtod;
u64 clock;
};
static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
static inline struct sched_clock_data *this_scd(void)
{
return this_cpu_ptr(&sched_clock_data);
}
static inline struct sched_clock_data *cpu_sdc(int cpu)
{
return &per_cpu(sched_clock_data, cpu);
}
int sched_clock_stable(void)
{
return static_branch_likely(&__sched_clock_stable);
}
static void __scd_stamp(struct sched_clock_data *scd)
{
scd->tick_gtod = ktime_get_ns();
scd->tick_raw = sched_clock();
}
sched/clock: Fixup early initialization The code would assume sched_clock_stable() and switch to !stable later, this switch brings a discontinuity in time. The discontinuity on switching from stable to unstable was always present, but previously we would set stable/unstable before initializing TSC and usually stick to the one we start out with. So the static_key bits brought an extra switch where there previously wasn't one. Things are further complicated by the fact that we cannot use static_key as early as we usually call set_sched_clock_stable(). Fix things by tracking the stable state in a regular variable and only set the static_key to the right state on sched_clock_init(), which is ran right after late_time_init->tsc_init(). Before this we would not be using the TSC anyway. Reported-and-Tested-by: Sasha Levin <sasha.levin@oracle.com> Reported-by: dyoung@redhat.com Fixes: 35af99e646c7 ("sched/clock, x86: Use a static_key for sched_clock_stable") Cc: jacob.jun.pan@linux.intel.com Cc: Mike Galbraith <bitbucket@online.de> Cc: hpa@zytor.com Cc: paulmck@linux.vnet.ibm.com Cc: John Stultz <john.stultz@linaro.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: lenb@kernel.org Cc: rjw@rjwysocki.net Cc: Eliezer Tamir <eliezer.tamir@linux.intel.com> Cc: rui.zhang@intel.com Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20140122115918.GG3694@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-01-22 11:59:18 +00:00
static void __set_sched_clock_stable(void)
{
struct sched_clock_data *scd;
sched/clock: Provide better clock continuity When switching between the unstable and stable variants it is currently possible that clock discontinuities occur. And while these will mostly be 'small', attempt to do better. As observed on my IVB-EP, the sched_clock() is ~1.5s ahead of the ktime_get_ns() based timeline at the point of switchover (sched_clock_init_late()) after SMP bringup. Equally, when the TSC is later found to be unstable -- typically because SMM tries to hide its SMI latencies by mucking with the TSC -- we want to avoid large jumps. Since the clocksource watchdog reports the issue after the fact we cannot exactly fix up time, but since SMI latencies are typically small (~10ns range), the discontinuity is mainly due to drift between sched_clock() and ktime_get_ns() (which on my desktop is ~79s over 24days). I dislike this patch because it adds overhead to the good case in favour of dealing with badness. But given the widespread failure of TSC stability this is worth it. Note that in case the TSC makes drastic jumps after SMP bringup we're still hosed. There's just not much we can do in that case without stupid overhead. If we were to somehow expose tsc_clocksource_reliable (which is hard because this code is also used on ia64 and parisc) we could avoid some of the newly introduced overhead. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-12-15 12:36:17 +00:00
/*
* Since we're still unstable and the tick is already running, we have
* to disable IRQs in order to get a consistent scd->tick* reading.
*/
local_irq_disable();
scd = this_scd();
sched/clock: Provide better clock continuity When switching between the unstable and stable variants it is currently possible that clock discontinuities occur. And while these will mostly be 'small', attempt to do better. As observed on my IVB-EP, the sched_clock() is ~1.5s ahead of the ktime_get_ns() based timeline at the point of switchover (sched_clock_init_late()) after SMP bringup. Equally, when the TSC is later found to be unstable -- typically because SMM tries to hide its SMI latencies by mucking with the TSC -- we want to avoid large jumps. Since the clocksource watchdog reports the issue after the fact we cannot exactly fix up time, but since SMI latencies are typically small (~10ns range), the discontinuity is mainly due to drift between sched_clock() and ktime_get_ns() (which on my desktop is ~79s over 24days). I dislike this patch because it adds overhead to the good case in favour of dealing with badness. But given the widespread failure of TSC stability this is worth it. Note that in case the TSC makes drastic jumps after SMP bringup we're still hosed. There's just not much we can do in that case without stupid overhead. If we were to somehow expose tsc_clocksource_reliable (which is hard because this code is also used on ia64 and parisc) we could avoid some of the newly introduced overhead. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-12-15 12:36:17 +00:00
/*
* Attempt to make the (initial) unstable->stable transition continuous.
*/
__sched_clock_offset = (scd->tick_gtod + __gtod_offset) - (scd->tick_raw);
local_irq_enable();
sched/clock: Provide better clock continuity When switching between the unstable and stable variants it is currently possible that clock discontinuities occur. And while these will mostly be 'small', attempt to do better. As observed on my IVB-EP, the sched_clock() is ~1.5s ahead of the ktime_get_ns() based timeline at the point of switchover (sched_clock_init_late()) after SMP bringup. Equally, when the TSC is later found to be unstable -- typically because SMM tries to hide its SMI latencies by mucking with the TSC -- we want to avoid large jumps. Since the clocksource watchdog reports the issue after the fact we cannot exactly fix up time, but since SMI latencies are typically small (~10ns range), the discontinuity is mainly due to drift between sched_clock() and ktime_get_ns() (which on my desktop is ~79s over 24days). I dislike this patch because it adds overhead to the good case in favour of dealing with badness. But given the widespread failure of TSC stability this is worth it. Note that in case the TSC makes drastic jumps after SMP bringup we're still hosed. There's just not much we can do in that case without stupid overhead. If we were to somehow expose tsc_clocksource_reliable (which is hard because this code is also used on ia64 and parisc) we could avoid some of the newly introduced overhead. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-12-15 12:36:17 +00:00
printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n",
scd->tick_gtod, __gtod_offset,
scd->tick_raw, __sched_clock_offset);
sched/clock: Provide better clock continuity When switching between the unstable and stable variants it is currently possible that clock discontinuities occur. And while these will mostly be 'small', attempt to do better. As observed on my IVB-EP, the sched_clock() is ~1.5s ahead of the ktime_get_ns() based timeline at the point of switchover (sched_clock_init_late()) after SMP bringup. Equally, when the TSC is later found to be unstable -- typically because SMM tries to hide its SMI latencies by mucking with the TSC -- we want to avoid large jumps. Since the clocksource watchdog reports the issue after the fact we cannot exactly fix up time, but since SMI latencies are typically small (~10ns range), the discontinuity is mainly due to drift between sched_clock() and ktime_get_ns() (which on my desktop is ~79s over 24days). I dislike this patch because it adds overhead to the good case in favour of dealing with badness. But given the widespread failure of TSC stability this is worth it. Note that in case the TSC makes drastic jumps after SMP bringup we're still hosed. There's just not much we can do in that case without stupid overhead. If we were to somehow expose tsc_clocksource_reliable (which is hard because this code is also used on ia64 and parisc) we could avoid some of the newly introduced overhead. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-12-15 12:36:17 +00:00
static_branch_enable(&__sched_clock_stable);
tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
sched/clock: Fixup early initialization The code would assume sched_clock_stable() and switch to !stable later, this switch brings a discontinuity in time. The discontinuity on switching from stable to unstable was always present, but previously we would set stable/unstable before initializing TSC and usually stick to the one we start out with. So the static_key bits brought an extra switch where there previously wasn't one. Things are further complicated by the fact that we cannot use static_key as early as we usually call set_sched_clock_stable(). Fix things by tracking the stable state in a regular variable and only set the static_key to the right state on sched_clock_init(), which is ran right after late_time_init->tsc_init(). Before this we would not be using the TSC anyway. Reported-and-Tested-by: Sasha Levin <sasha.levin@oracle.com> Reported-by: dyoung@redhat.com Fixes: 35af99e646c7 ("sched/clock, x86: Use a static_key for sched_clock_stable") Cc: jacob.jun.pan@linux.intel.com Cc: Mike Galbraith <bitbucket@online.de> Cc: hpa@zytor.com Cc: paulmck@linux.vnet.ibm.com Cc: John Stultz <john.stultz@linaro.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: lenb@kernel.org Cc: rjw@rjwysocki.net Cc: Eliezer Tamir <eliezer.tamir@linux.intel.com> Cc: rui.zhang@intel.com Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20140122115918.GG3694@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-01-22 11:59:18 +00:00
}
/*
* If we ever get here, we're screwed, because we found out -- typically after
* the fact -- that TSC wasn't good. This means all our clocksources (including
* ktime) could have reported wrong values.
*
* What we do here is an attempt to fix up and continue sort of where we left
* off in a coherent manner.
*
* The only way to fully avoid random clock jumps is to boot with:
* "tsc=unstable".
*/
static void __sched_clock_work(struct work_struct *work)
{
struct sched_clock_data *scd;
int cpu;
/* take a current timestamp and set 'now' */
preempt_disable();
scd = this_scd();
__scd_stamp(scd);
scd->clock = scd->tick_gtod + __gtod_offset;
preempt_enable();
/* clone to all CPUs */
for_each_possible_cpu(cpu)
per_cpu(sched_clock_data, cpu) = *scd;
printk(KERN_WARNING "TSC found unstable after boot, most likely due to broken BIOS. Use 'tsc=unstable'.\n");
printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n",
scd->tick_gtod, __gtod_offset,
scd->tick_raw, __sched_clock_offset);
static_branch_disable(&__sched_clock_stable);
}
static DECLARE_WORK(sched_clock_work, __sched_clock_work);
static void __clear_sched_clock_stable(void)
{
if (!sched_clock_stable())
return;
sched/clock: Provide better clock continuity When switching between the unstable and stable variants it is currently possible that clock discontinuities occur. And while these will mostly be 'small', attempt to do better. As observed on my IVB-EP, the sched_clock() is ~1.5s ahead of the ktime_get_ns() based timeline at the point of switchover (sched_clock_init_late()) after SMP bringup. Equally, when the TSC is later found to be unstable -- typically because SMM tries to hide its SMI latencies by mucking with the TSC -- we want to avoid large jumps. Since the clocksource watchdog reports the issue after the fact we cannot exactly fix up time, but since SMI latencies are typically small (~10ns range), the discontinuity is mainly due to drift between sched_clock() and ktime_get_ns() (which on my desktop is ~79s over 24days). I dislike this patch because it adds overhead to the good case in favour of dealing with badness. But given the widespread failure of TSC stability this is worth it. Note that in case the TSC makes drastic jumps after SMP bringup we're still hosed. There's just not much we can do in that case without stupid overhead. If we were to somehow expose tsc_clocksource_reliable (which is hard because this code is also used on ia64 and parisc) we could avoid some of the newly introduced overhead. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-12-15 12:36:17 +00:00
tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE);
schedule_work(&sched_clock_work);
}
sched/clock: Fix up clear_sched_clock_stable() The below tells us the static_key conversion has a problem; since the exact point of clearing that flag isn't too important, delay the flip and use a workqueue to process it. [ ] TSC synchronization [CPU#0 -> CPU#22]: [ ] Measured 8 cycles TSC warp between CPUs, turning off TSC clock. [ ] [ ] ====================================================== [ ] [ INFO: possible circular locking dependency detected ] [ ] 3.13.0-rc3-01745-g848b0d0322cb-dirty #637 Not tainted [ ] ------------------------------------------------------- [ ] swapper/0/1 is trying to acquire lock: [ ] (jump_label_mutex){+.+...}, at: [<ffffffff8115a637>] jump_label_lock+0x17/0x20 [ ] [ ] but task is already holding lock: [ ] (cpu_hotplug.lock){+.+.+.}, at: [<ffffffff8109408b>] cpu_hotplug_begin+0x2b/0x60 [ ] [ ] which lock already depends on the new lock. [ ] [ ] [ ] the existing dependency chain (in reverse order) is: [ ] [ ] -> #1 (cpu_hotplug.lock){+.+.+.}: [ ] [<ffffffff810def00>] lock_acquire+0x90/0x130 [ ] [<ffffffff81661f83>] mutex_lock_nested+0x63/0x3e0 [ ] [<ffffffff81093fdc>] get_online_cpus+0x3c/0x60 [ ] [<ffffffff8104cc67>] arch_jump_label_transform+0x37/0x130 [ ] [<ffffffff8115a3cf>] __jump_label_update+0x5f/0x80 [ ] [<ffffffff8115a48d>] jump_label_update+0x9d/0xb0 [ ] [<ffffffff8115aa6d>] static_key_slow_inc+0x9d/0xb0 [ ] [<ffffffff810c0f65>] sched_feat_set+0xf5/0x100 [ ] [<ffffffff810c5bdc>] set_numabalancing_state+0x2c/0x30 [ ] [<ffffffff81d12f3d>] numa_policy_init+0x1af/0x1b7 [ ] [<ffffffff81cebdf4>] start_kernel+0x35d/0x41f [ ] [<ffffffff81ceb5a5>] x86_64_start_reservations+0x2a/0x2c [ ] [<ffffffff81ceb6a2>] x86_64_start_kernel+0xfb/0xfe [ ] [ ] -> #0 (jump_label_mutex){+.+...}: [ ] [<ffffffff810de141>] __lock_acquire+0x1701/0x1eb0 [ ] [<ffffffff810def00>] lock_acquire+0x90/0x130 [ ] [<ffffffff81661f83>] mutex_lock_nested+0x63/0x3e0 [ ] [<ffffffff8115a637>] jump_label_lock+0x17/0x20 [ ] [<ffffffff8115aa3b>] static_key_slow_inc+0x6b/0xb0 [ ] [<ffffffff810ca775>] clear_sched_clock_stable+0x15/0x20 [ ] [<ffffffff810503b3>] mark_tsc_unstable+0x23/0x70 [ ] [<ffffffff810772cb>] check_tsc_sync_source+0x14b/0x150 [ ] [<ffffffff81076612>] native_cpu_up+0x3a2/0x890 [ ] [<ffffffff810941cb>] _cpu_up+0xdb/0x160 [ ] [<ffffffff810942c9>] cpu_up+0x79/0x90 [ ] [<ffffffff81d0af6b>] smp_init+0x60/0x8c [ ] [<ffffffff81cebf42>] kernel_init_freeable+0x8c/0x197 [ ] [<ffffffff8164e32e>] kernel_init+0xe/0x130 [ ] [<ffffffff8166beec>] ret_from_fork+0x7c/0xb0 [ ] [ ] other info that might help us debug this: [ ] [ ] Possible unsafe locking scenario: [ ] [ ] CPU0 CPU1 [ ] ---- ---- [ ] lock(cpu_hotplug.lock); [ ] lock(jump_label_mutex); [ ] lock(cpu_hotplug.lock); [ ] lock(jump_label_mutex); [ ] [ ] *** DEADLOCK *** [ ] [ ] 2 locks held by swapper/0/1: [ ] #0: (cpu_add_remove_lock){+.+.+.}, at: [<ffffffff81094037>] cpu_maps_update_begin+0x17/0x20 [ ] #1: (cpu_hotplug.lock){+.+.+.}, at: [<ffffffff8109408b>] cpu_hotplug_begin+0x2b/0x60 [ ] [ ] stack backtrace: [ ] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.13.0-rc3-01745-g848b0d0322cb-dirty #637 [ ] Hardware name: Supermicro X8DTN/X8DTN, BIOS 4.6.3 01/08/2010 [ ] ffffffff82c9c270 ffff880236843bb8 ffffffff8165c5f5 ffffffff82c9c270 [ ] ffff880236843bf8 ffffffff81658c02 ffff880236843c80 ffff8802368586a0 [ ] ffff880236858678 0000000000000001 0000000000000002 ffff880236858000 [ ] Call Trace: [ ] [<ffffffff8165c5f5>] dump_stack+0x4e/0x7a [ ] [<ffffffff81658c02>] print_circular_bug+0x1f9/0x207 [ ] [<ffffffff810de141>] __lock_acquire+0x1701/0x1eb0 [ ] [<ffffffff816680ff>] ? __atomic_notifier_call_chain+0x8f/0xb0 [ ] [<ffffffff810def00>] lock_acquire+0x90/0x130 [ ] [<ffffffff8115a637>] ? jump_label_lock+0x17/0x20 [ ] [<ffffffff8115a637>] ? jump_label_lock+0x17/0x20 [ ] [<ffffffff81661f83>] mutex_lock_nested+0x63/0x3e0 [ ] [<ffffffff8115a637>] ? jump_label_lock+0x17/0x20 [ ] [<ffffffff8115a637>] jump_label_lock+0x17/0x20 [ ] [<ffffffff8115aa3b>] static_key_slow_inc+0x6b/0xb0 [ ] [<ffffffff810ca775>] clear_sched_clock_stable+0x15/0x20 [ ] [<ffffffff810503b3>] mark_tsc_unstable+0x23/0x70 [ ] [<ffffffff810772cb>] check_tsc_sync_source+0x14b/0x150 [ ] [<ffffffff81076612>] native_cpu_up+0x3a2/0x890 [ ] [<ffffffff810941cb>] _cpu_up+0xdb/0x160 [ ] [<ffffffff810942c9>] cpu_up+0x79/0x90 [ ] [<ffffffff81d0af6b>] smp_init+0x60/0x8c [ ] [<ffffffff81cebf42>] kernel_init_freeable+0x8c/0x197 [ ] [<ffffffff8164e320>] ? rest_init+0xd0/0xd0 [ ] [<ffffffff8164e32e>] kernel_init+0xe/0x130 [ ] [<ffffffff8166beec>] ret_from_fork+0x7c/0xb0 [ ] [<ffffffff8164e320>] ? rest_init+0xd0/0xd0 [ ] ------------[ cut here ]------------ [ ] WARNING: CPU: 0 PID: 1 at /usr/src/linux-2.6/kernel/smp.c:374 smp_call_function_many+0xad/0x300() [ ] Modules linked in: [ ] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.13.0-rc3-01745-g848b0d0322cb-dirty #637 [ ] Hardware name: Supermicro X8DTN/X8DTN, BIOS 4.6.3 01/08/2010 [ ] 0000000000000009 ffff880236843be0 ffffffff8165c5f5 0000000000000000 [ ] ffff880236843c18 ffffffff81093d8c 0000000000000000 0000000000000000 [ ] ffffffff81ccd1a0 ffffffff810ca951 0000000000000000 ffff880236843c28 [ ] Call Trace: [ ] [<ffffffff8165c5f5>] dump_stack+0x4e/0x7a [ ] [<ffffffff81093d8c>] warn_slowpath_common+0x8c/0xc0 [ ] [<ffffffff810ca951>] ? sched_clock_tick+0x1/0xa0 [ ] [<ffffffff81093dda>] warn_slowpath_null+0x1a/0x20 [ ] [<ffffffff8110b72d>] smp_call_function_many+0xad/0x300 [ ] [<ffffffff8104f200>] ? arch_unregister_cpu+0x30/0x30 [ ] [<ffffffff8104f200>] ? arch_unregister_cpu+0x30/0x30 [ ] [<ffffffff810ca951>] ? sched_clock_tick+0x1/0xa0 [ ] [<ffffffff8110ba96>] smp_call_function+0x46/0x80 [ ] [<ffffffff8104f200>] ? arch_unregister_cpu+0x30/0x30 [ ] [<ffffffff8110bb3c>] on_each_cpu+0x3c/0xa0 [ ] [<ffffffff810ca950>] ? sched_clock_idle_sleep_event+0x20/0x20 [ ] [<ffffffff810ca951>] ? sched_clock_tick+0x1/0xa0 [ ] [<ffffffff8104f964>] text_poke_bp+0x64/0xd0 [ ] [<ffffffff810ca950>] ? sched_clock_idle_sleep_event+0x20/0x20 [ ] [<ffffffff8104ccde>] arch_jump_label_transform+0xae/0x130 [ ] [<ffffffff8115a3cf>] __jump_label_update+0x5f/0x80 [ ] [<ffffffff8115a48d>] jump_label_update+0x9d/0xb0 [ ] [<ffffffff8115aa6d>] static_key_slow_inc+0x9d/0xb0 [ ] [<ffffffff810ca775>] clear_sched_clock_stable+0x15/0x20 [ ] [<ffffffff810503b3>] mark_tsc_unstable+0x23/0x70 [ ] [<ffffffff810772cb>] check_tsc_sync_source+0x14b/0x150 [ ] [<ffffffff81076612>] native_cpu_up+0x3a2/0x890 [ ] [<ffffffff810941cb>] _cpu_up+0xdb/0x160 [ ] [<ffffffff810942c9>] cpu_up+0x79/0x90 [ ] [<ffffffff81d0af6b>] smp_init+0x60/0x8c [ ] [<ffffffff81cebf42>] kernel_init_freeable+0x8c/0x197 [ ] [<ffffffff8164e320>] ? rest_init+0xd0/0xd0 [ ] [<ffffffff8164e32e>] kernel_init+0xe/0x130 [ ] [<ffffffff8166beec>] ret_from_fork+0x7c/0xb0 [ ] [<ffffffff8164e320>] ? rest_init+0xd0/0xd0 [ ] ---[ end trace 6ff1df5620c49d26 ]--- [ ] tsc: Marking TSC unstable due to check_tsc_sync_source failed Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/n/tip-v55fgqj3nnyqnngmvuu8ep6h@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-12-11 17:55:53 +00:00
void clear_sched_clock_stable(void)
{
sched/clock: Fixup early initialization The code would assume sched_clock_stable() and switch to !stable later, this switch brings a discontinuity in time. The discontinuity on switching from stable to unstable was always present, but previously we would set stable/unstable before initializing TSC and usually stick to the one we start out with. So the static_key bits brought an extra switch where there previously wasn't one. Things are further complicated by the fact that we cannot use static_key as early as we usually call set_sched_clock_stable(). Fix things by tracking the stable state in a regular variable and only set the static_key to the right state on sched_clock_init(), which is ran right after late_time_init->tsc_init(). Before this we would not be using the TSC anyway. Reported-and-Tested-by: Sasha Levin <sasha.levin@oracle.com> Reported-by: dyoung@redhat.com Fixes: 35af99e646c7 ("sched/clock, x86: Use a static_key for sched_clock_stable") Cc: jacob.jun.pan@linux.intel.com Cc: Mike Galbraith <bitbucket@online.de> Cc: hpa@zytor.com Cc: paulmck@linux.vnet.ibm.com Cc: John Stultz <john.stultz@linaro.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: lenb@kernel.org Cc: rjw@rjwysocki.net Cc: Eliezer Tamir <eliezer.tamir@linux.intel.com> Cc: rui.zhang@intel.com Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20140122115918.GG3694@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-01-22 11:59:18 +00:00
__sched_clock_stable_early = 0;
smp_mb(); /* matches sched_clock_init_late() */
sched/clock: Fixup early initialization The code would assume sched_clock_stable() and switch to !stable later, this switch brings a discontinuity in time. The discontinuity on switching from stable to unstable was always present, but previously we would set stable/unstable before initializing TSC and usually stick to the one we start out with. So the static_key bits brought an extra switch where there previously wasn't one. Things are further complicated by the fact that we cannot use static_key as early as we usually call set_sched_clock_stable(). Fix things by tracking the stable state in a regular variable and only set the static_key to the right state on sched_clock_init(), which is ran right after late_time_init->tsc_init(). Before this we would not be using the TSC anyway. Reported-and-Tested-by: Sasha Levin <sasha.levin@oracle.com> Reported-by: dyoung@redhat.com Fixes: 35af99e646c7 ("sched/clock, x86: Use a static_key for sched_clock_stable") Cc: jacob.jun.pan@linux.intel.com Cc: Mike Galbraith <bitbucket@online.de> Cc: hpa@zytor.com Cc: paulmck@linux.vnet.ibm.com Cc: John Stultz <john.stultz@linaro.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: lenb@kernel.org Cc: rjw@rjwysocki.net Cc: Eliezer Tamir <eliezer.tamir@linux.intel.com> Cc: rui.zhang@intel.com Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20140122115918.GG3694@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-01-22 11:59:18 +00:00
if (static_key_count(&sched_clock_running.key) == 2)
__clear_sched_clock_stable();
sched/clock: Fix up clear_sched_clock_stable() The below tells us the static_key conversion has a problem; since the exact point of clearing that flag isn't too important, delay the flip and use a workqueue to process it. [ ] TSC synchronization [CPU#0 -> CPU#22]: [ ] Measured 8 cycles TSC warp between CPUs, turning off TSC clock. [ ] [ ] ====================================================== [ ] [ INFO: possible circular locking dependency detected ] [ ] 3.13.0-rc3-01745-g848b0d0322cb-dirty #637 Not tainted [ ] ------------------------------------------------------- [ ] swapper/0/1 is trying to acquire lock: [ ] (jump_label_mutex){+.+...}, at: [<ffffffff8115a637>] jump_label_lock+0x17/0x20 [ ] [ ] but task is already holding lock: [ ] (cpu_hotplug.lock){+.+.+.}, at: [<ffffffff8109408b>] cpu_hotplug_begin+0x2b/0x60 [ ] [ ] which lock already depends on the new lock. [ ] [ ] [ ] the existing dependency chain (in reverse order) is: [ ] [ ] -> #1 (cpu_hotplug.lock){+.+.+.}: [ ] [<ffffffff810def00>] lock_acquire+0x90/0x130 [ ] [<ffffffff81661f83>] mutex_lock_nested+0x63/0x3e0 [ ] [<ffffffff81093fdc>] get_online_cpus+0x3c/0x60 [ ] [<ffffffff8104cc67>] arch_jump_label_transform+0x37/0x130 [ ] [<ffffffff8115a3cf>] __jump_label_update+0x5f/0x80 [ ] [<ffffffff8115a48d>] jump_label_update+0x9d/0xb0 [ ] [<ffffffff8115aa6d>] static_key_slow_inc+0x9d/0xb0 [ ] [<ffffffff810c0f65>] sched_feat_set+0xf5/0x100 [ ] [<ffffffff810c5bdc>] set_numabalancing_state+0x2c/0x30 [ ] [<ffffffff81d12f3d>] numa_policy_init+0x1af/0x1b7 [ ] [<ffffffff81cebdf4>] start_kernel+0x35d/0x41f [ ] [<ffffffff81ceb5a5>] x86_64_start_reservations+0x2a/0x2c [ ] [<ffffffff81ceb6a2>] x86_64_start_kernel+0xfb/0xfe [ ] [ ] -> #0 (jump_label_mutex){+.+...}: [ ] [<ffffffff810de141>] __lock_acquire+0x1701/0x1eb0 [ ] [<ffffffff810def00>] lock_acquire+0x90/0x130 [ ] [<ffffffff81661f83>] mutex_lock_nested+0x63/0x3e0 [ ] [<ffffffff8115a637>] jump_label_lock+0x17/0x20 [ ] [<ffffffff8115aa3b>] static_key_slow_inc+0x6b/0xb0 [ ] [<ffffffff810ca775>] clear_sched_clock_stable+0x15/0x20 [ ] [<ffffffff810503b3>] mark_tsc_unstable+0x23/0x70 [ ] [<ffffffff810772cb>] check_tsc_sync_source+0x14b/0x150 [ ] [<ffffffff81076612>] native_cpu_up+0x3a2/0x890 [ ] [<ffffffff810941cb>] _cpu_up+0xdb/0x160 [ ] [<ffffffff810942c9>] cpu_up+0x79/0x90 [ ] [<ffffffff81d0af6b>] smp_init+0x60/0x8c [ ] [<ffffffff81cebf42>] kernel_init_freeable+0x8c/0x197 [ ] [<ffffffff8164e32e>] kernel_init+0xe/0x130 [ ] [<ffffffff8166beec>] ret_from_fork+0x7c/0xb0 [ ] [ ] other info that might help us debug this: [ ] [ ] Possible unsafe locking scenario: [ ] [ ] CPU0 CPU1 [ ] ---- ---- [ ] lock(cpu_hotplug.lock); [ ] lock(jump_label_mutex); [ ] lock(cpu_hotplug.lock); [ ] lock(jump_label_mutex); [ ] [ ] *** DEADLOCK *** [ ] [ ] 2 locks held by swapper/0/1: [ ] #0: (cpu_add_remove_lock){+.+.+.}, at: [<ffffffff81094037>] cpu_maps_update_begin+0x17/0x20 [ ] #1: (cpu_hotplug.lock){+.+.+.}, at: [<ffffffff8109408b>] cpu_hotplug_begin+0x2b/0x60 [ ] [ ] stack backtrace: [ ] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.13.0-rc3-01745-g848b0d0322cb-dirty #637 [ ] Hardware name: Supermicro X8DTN/X8DTN, BIOS 4.6.3 01/08/2010 [ ] ffffffff82c9c270 ffff880236843bb8 ffffffff8165c5f5 ffffffff82c9c270 [ ] ffff880236843bf8 ffffffff81658c02 ffff880236843c80 ffff8802368586a0 [ ] ffff880236858678 0000000000000001 0000000000000002 ffff880236858000 [ ] Call Trace: [ ] [<ffffffff8165c5f5>] dump_stack+0x4e/0x7a [ ] [<ffffffff81658c02>] print_circular_bug+0x1f9/0x207 [ ] [<ffffffff810de141>] __lock_acquire+0x1701/0x1eb0 [ ] [<ffffffff816680ff>] ? __atomic_notifier_call_chain+0x8f/0xb0 [ ] [<ffffffff810def00>] lock_acquire+0x90/0x130 [ ] [<ffffffff8115a637>] ? jump_label_lock+0x17/0x20 [ ] [<ffffffff8115a637>] ? jump_label_lock+0x17/0x20 [ ] [<ffffffff81661f83>] mutex_lock_nested+0x63/0x3e0 [ ] [<ffffffff8115a637>] ? jump_label_lock+0x17/0x20 [ ] [<ffffffff8115a637>] jump_label_lock+0x17/0x20 [ ] [<ffffffff8115aa3b>] static_key_slow_inc+0x6b/0xb0 [ ] [<ffffffff810ca775>] clear_sched_clock_stable+0x15/0x20 [ ] [<ffffffff810503b3>] mark_tsc_unstable+0x23/0x70 [ ] [<ffffffff810772cb>] check_tsc_sync_source+0x14b/0x150 [ ] [<ffffffff81076612>] native_cpu_up+0x3a2/0x890 [ ] [<ffffffff810941cb>] _cpu_up+0xdb/0x160 [ ] [<ffffffff810942c9>] cpu_up+0x79/0x90 [ ] [<ffffffff81d0af6b>] smp_init+0x60/0x8c [ ] [<ffffffff81cebf42>] kernel_init_freeable+0x8c/0x197 [ ] [<ffffffff8164e320>] ? rest_init+0xd0/0xd0 [ ] [<ffffffff8164e32e>] kernel_init+0xe/0x130 [ ] [<ffffffff8166beec>] ret_from_fork+0x7c/0xb0 [ ] [<ffffffff8164e320>] ? rest_init+0xd0/0xd0 [ ] ------------[ cut here ]------------ [ ] WARNING: CPU: 0 PID: 1 at /usr/src/linux-2.6/kernel/smp.c:374 smp_call_function_many+0xad/0x300() [ ] Modules linked in: [ ] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.13.0-rc3-01745-g848b0d0322cb-dirty #637 [ ] Hardware name: Supermicro X8DTN/X8DTN, BIOS 4.6.3 01/08/2010 [ ] 0000000000000009 ffff880236843be0 ffffffff8165c5f5 0000000000000000 [ ] ffff880236843c18 ffffffff81093d8c 0000000000000000 0000000000000000 [ ] ffffffff81ccd1a0 ffffffff810ca951 0000000000000000 ffff880236843c28 [ ] Call Trace: [ ] [<ffffffff8165c5f5>] dump_stack+0x4e/0x7a [ ] [<ffffffff81093d8c>] warn_slowpath_common+0x8c/0xc0 [ ] [<ffffffff810ca951>] ? sched_clock_tick+0x1/0xa0 [ ] [<ffffffff81093dda>] warn_slowpath_null+0x1a/0x20 [ ] [<ffffffff8110b72d>] smp_call_function_many+0xad/0x300 [ ] [<ffffffff8104f200>] ? arch_unregister_cpu+0x30/0x30 [ ] [<ffffffff8104f200>] ? arch_unregister_cpu+0x30/0x30 [ ] [<ffffffff810ca951>] ? sched_clock_tick+0x1/0xa0 [ ] [<ffffffff8110ba96>] smp_call_function+0x46/0x80 [ ] [<ffffffff8104f200>] ? arch_unregister_cpu+0x30/0x30 [ ] [<ffffffff8110bb3c>] on_each_cpu+0x3c/0xa0 [ ] [<ffffffff810ca950>] ? sched_clock_idle_sleep_event+0x20/0x20 [ ] [<ffffffff810ca951>] ? sched_clock_tick+0x1/0xa0 [ ] [<ffffffff8104f964>] text_poke_bp+0x64/0xd0 [ ] [<ffffffff810ca950>] ? sched_clock_idle_sleep_event+0x20/0x20 [ ] [<ffffffff8104ccde>] arch_jump_label_transform+0xae/0x130 [ ] [<ffffffff8115a3cf>] __jump_label_update+0x5f/0x80 [ ] [<ffffffff8115a48d>] jump_label_update+0x9d/0xb0 [ ] [<ffffffff8115aa6d>] static_key_slow_inc+0x9d/0xb0 [ ] [<ffffffff810ca775>] clear_sched_clock_stable+0x15/0x20 [ ] [<ffffffff810503b3>] mark_tsc_unstable+0x23/0x70 [ ] [<ffffffff810772cb>] check_tsc_sync_source+0x14b/0x150 [ ] [<ffffffff81076612>] native_cpu_up+0x3a2/0x890 [ ] [<ffffffff810941cb>] _cpu_up+0xdb/0x160 [ ] [<ffffffff810942c9>] cpu_up+0x79/0x90 [ ] [<ffffffff81d0af6b>] smp_init+0x60/0x8c [ ] [<ffffffff81cebf42>] kernel_init_freeable+0x8c/0x197 [ ] [<ffffffff8164e320>] ? rest_init+0xd0/0xd0 [ ] [<ffffffff8164e32e>] kernel_init+0xe/0x130 [ ] [<ffffffff8166beec>] ret_from_fork+0x7c/0xb0 [ ] [<ffffffff8164e320>] ? rest_init+0xd0/0xd0 [ ] ---[ end trace 6ff1df5620c49d26 ]--- [ ] tsc: Marking TSC unstable due to check_tsc_sync_source failed Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/n/tip-v55fgqj3nnyqnngmvuu8ep6h@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-12-11 17:55:53 +00:00
}
static void __sched_clock_gtod_offset(void)
{
struct sched_clock_data *scd = this_scd();
__scd_stamp(scd);
__gtod_offset = (scd->tick_raw + __sched_clock_offset) - scd->tick_gtod;
}
void __init sched_clock_init(void)
{
/*
* Set __gtod_offset such that once we mark sched_clock_running,
* sched_clock_tick() continues where sched_clock() left off.
*
* Even if TSC is buggered, we're still UP at this point so it
* can't really be out of sync.
*/
local_irq_disable();
__sched_clock_gtod_offset();
local_irq_enable();
static_branch_inc(&sched_clock_running);
}
/*
* We run this as late_initcall() such that it runs after all built-in drivers,
* notably: acpi_processor and intel_idle, which can mark the TSC as unstable.
*/
static int __init sched_clock_init_late(void)
{
static_branch_inc(&sched_clock_running);
sched/clock: Fixup early initialization The code would assume sched_clock_stable() and switch to !stable later, this switch brings a discontinuity in time. The discontinuity on switching from stable to unstable was always present, but previously we would set stable/unstable before initializing TSC and usually stick to the one we start out with. So the static_key bits brought an extra switch where there previously wasn't one. Things are further complicated by the fact that we cannot use static_key as early as we usually call set_sched_clock_stable(). Fix things by tracking the stable state in a regular variable and only set the static_key to the right state on sched_clock_init(), which is ran right after late_time_init->tsc_init(). Before this we would not be using the TSC anyway. Reported-and-Tested-by: Sasha Levin <sasha.levin@oracle.com> Reported-by: dyoung@redhat.com Fixes: 35af99e646c7 ("sched/clock, x86: Use a static_key for sched_clock_stable") Cc: jacob.jun.pan@linux.intel.com Cc: Mike Galbraith <bitbucket@online.de> Cc: hpa@zytor.com Cc: paulmck@linux.vnet.ibm.com Cc: John Stultz <john.stultz@linaro.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: lenb@kernel.org Cc: rjw@rjwysocki.net Cc: Eliezer Tamir <eliezer.tamir@linux.intel.com> Cc: rui.zhang@intel.com Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20140122115918.GG3694@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-01-22 11:59:18 +00:00
/*
* Ensure that it is impossible to not do a static_key update.
*
* Either {set,clear}_sched_clock_stable() must see sched_clock_running
* and do the update, or we must see their __sched_clock_stable_early
* and do the update, or both.
*/
smp_mb(); /* matches {set,clear}_sched_clock_stable() */
if (__sched_clock_stable_early)
__set_sched_clock_stable();
return 0;
}
late_initcall(sched_clock_init_late);
sched_clock: fix cpu_clock() This patch fixes 3 issues: a) it removes the dependency on jiffies, because jiffies are incremented by a single CPU, and the tick is not synchronized between CPUs. Therefore relying on it to calculate a window to clip whacky TSC values doesn't work as it can drift around. So instead use [GTOD, GTOD+TICK_NSEC) as the window. b) __update_sched_clock() did (roughly speaking): delta = sched_clock() - scd->tick_raw; clock += delta; Which gives exponential growth, instead of linear. c) allows the sched_clock_cpu() value to warp the u64 without breaking. the results are more reliable sched_clock() deltas: before after sched_clock cpu_clock: 15750 51312 51488 cpu_clock: 59719 51052 50947 cpu_clock: 15879 51249 51061 cpu_clock: 1 50933 51198 cpu_clock: 1 50931 51039 cpu_clock: 1 51093 50981 cpu_clock: 1 51043 51040 cpu_clock: 1 50959 50938 cpu_clock: 1 50981 51011 cpu_clock: 1 51364 51212 cpu_clock: 1 51219 51273 cpu_clock: 1 51389 51048 cpu_clock: 1 51285 51611 cpu_clock: 1 50964 51137 cpu_clock: 1 50973 50968 cpu_clock: 1 50967 50972 cpu_clock: 1 58910 58485 cpu_clock: 1 51082 51025 cpu_clock: 1 50957 50958 cpu_clock: 1 50958 50957 cpu_clock: 1006128 51128 50971 cpu_clock: 1 51107 51155 cpu_clock: 1 51371 51081 cpu_clock: 1 51104 51365 cpu_clock: 1 51363 51309 cpu_clock: 1 51107 51160 cpu_clock: 1 51139 51100 cpu_clock: 1 51216 51136 cpu_clock: 1 51207 51215 cpu_clock: 1 51087 51263 cpu_clock: 1 51249 51177 cpu_clock: 1 51519 51412 cpu_clock: 1 51416 51255 cpu_clock: 1 51591 51594 cpu_clock: 1 50966 51374 cpu_clock: 1 50966 50966 cpu_clock: 1 51291 50948 cpu_clock: 1 50973 50867 cpu_clock: 1 50970 50970 cpu_clock: 998306 50970 50971 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 50971 50971 cpu_clock: 1 50970 50970 cpu_clock: 1 51351 50970 cpu_clock: 1 50970 51352 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 51321 50971 cpu_clock: 1 50974 51324 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-25 15:15:34 +00:00
/*
* min, max except they take wrapping into account
sched_clock: fix cpu_clock() This patch fixes 3 issues: a) it removes the dependency on jiffies, because jiffies are incremented by a single CPU, and the tick is not synchronized between CPUs. Therefore relying on it to calculate a window to clip whacky TSC values doesn't work as it can drift around. So instead use [GTOD, GTOD+TICK_NSEC) as the window. b) __update_sched_clock() did (roughly speaking): delta = sched_clock() - scd->tick_raw; clock += delta; Which gives exponential growth, instead of linear. c) allows the sched_clock_cpu() value to warp the u64 without breaking. the results are more reliable sched_clock() deltas: before after sched_clock cpu_clock: 15750 51312 51488 cpu_clock: 59719 51052 50947 cpu_clock: 15879 51249 51061 cpu_clock: 1 50933 51198 cpu_clock: 1 50931 51039 cpu_clock: 1 51093 50981 cpu_clock: 1 51043 51040 cpu_clock: 1 50959 50938 cpu_clock: 1 50981 51011 cpu_clock: 1 51364 51212 cpu_clock: 1 51219 51273 cpu_clock: 1 51389 51048 cpu_clock: 1 51285 51611 cpu_clock: 1 50964 51137 cpu_clock: 1 50973 50968 cpu_clock: 1 50967 50972 cpu_clock: 1 58910 58485 cpu_clock: 1 51082 51025 cpu_clock: 1 50957 50958 cpu_clock: 1 50958 50957 cpu_clock: 1006128 51128 50971 cpu_clock: 1 51107 51155 cpu_clock: 1 51371 51081 cpu_clock: 1 51104 51365 cpu_clock: 1 51363 51309 cpu_clock: 1 51107 51160 cpu_clock: 1 51139 51100 cpu_clock: 1 51216 51136 cpu_clock: 1 51207 51215 cpu_clock: 1 51087 51263 cpu_clock: 1 51249 51177 cpu_clock: 1 51519 51412 cpu_clock: 1 51416 51255 cpu_clock: 1 51591 51594 cpu_clock: 1 50966 51374 cpu_clock: 1 50966 50966 cpu_clock: 1 51291 50948 cpu_clock: 1 50973 50867 cpu_clock: 1 50970 50970 cpu_clock: 998306 50970 50971 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 50971 50971 cpu_clock: 1 50970 50970 cpu_clock: 1 51351 50970 cpu_clock: 1 50970 51352 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 51321 50971 cpu_clock: 1 50974 51324 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-25 15:15:34 +00:00
*/
static inline u64 wrap_min(u64 x, u64 y)
{
return (s64)(x - y) < 0 ? x : y;
}
static inline u64 wrap_max(u64 x, u64 y)
{
return (s64)(x - y) > 0 ? x : y;
}
/*
* update the percpu scd from the raw @now value
*
* - filter out backward motion
sched_clock: fix cpu_clock() This patch fixes 3 issues: a) it removes the dependency on jiffies, because jiffies are incremented by a single CPU, and the tick is not synchronized between CPUs. Therefore relying on it to calculate a window to clip whacky TSC values doesn't work as it can drift around. So instead use [GTOD, GTOD+TICK_NSEC) as the window. b) __update_sched_clock() did (roughly speaking): delta = sched_clock() - scd->tick_raw; clock += delta; Which gives exponential growth, instead of linear. c) allows the sched_clock_cpu() value to warp the u64 without breaking. the results are more reliable sched_clock() deltas: before after sched_clock cpu_clock: 15750 51312 51488 cpu_clock: 59719 51052 50947 cpu_clock: 15879 51249 51061 cpu_clock: 1 50933 51198 cpu_clock: 1 50931 51039 cpu_clock: 1 51093 50981 cpu_clock: 1 51043 51040 cpu_clock: 1 50959 50938 cpu_clock: 1 50981 51011 cpu_clock: 1 51364 51212 cpu_clock: 1 51219 51273 cpu_clock: 1 51389 51048 cpu_clock: 1 51285 51611 cpu_clock: 1 50964 51137 cpu_clock: 1 50973 50968 cpu_clock: 1 50967 50972 cpu_clock: 1 58910 58485 cpu_clock: 1 51082 51025 cpu_clock: 1 50957 50958 cpu_clock: 1 50958 50957 cpu_clock: 1006128 51128 50971 cpu_clock: 1 51107 51155 cpu_clock: 1 51371 51081 cpu_clock: 1 51104 51365 cpu_clock: 1 51363 51309 cpu_clock: 1 51107 51160 cpu_clock: 1 51139 51100 cpu_clock: 1 51216 51136 cpu_clock: 1 51207 51215 cpu_clock: 1 51087 51263 cpu_clock: 1 51249 51177 cpu_clock: 1 51519 51412 cpu_clock: 1 51416 51255 cpu_clock: 1 51591 51594 cpu_clock: 1 50966 51374 cpu_clock: 1 50966 50966 cpu_clock: 1 51291 50948 cpu_clock: 1 50973 50867 cpu_clock: 1 50970 50970 cpu_clock: 998306 50970 50971 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 50971 50971 cpu_clock: 1 50970 50970 cpu_clock: 1 51351 50970 cpu_clock: 1 50970 51352 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 51321 50971 cpu_clock: 1 50974 51324 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-25 15:15:34 +00:00
* - use the GTOD tick value to create a window to filter crazy TSC values
*/
static u64 sched_clock_local(struct sched_clock_data *scd)
{
u64 now, clock, old_clock, min_clock, max_clock, gtod;
s64 delta;
again:
now = sched_clock();
delta = now - scd->tick_raw;
sched_clock: fix cpu_clock() This patch fixes 3 issues: a) it removes the dependency on jiffies, because jiffies are incremented by a single CPU, and the tick is not synchronized between CPUs. Therefore relying on it to calculate a window to clip whacky TSC values doesn't work as it can drift around. So instead use [GTOD, GTOD+TICK_NSEC) as the window. b) __update_sched_clock() did (roughly speaking): delta = sched_clock() - scd->tick_raw; clock += delta; Which gives exponential growth, instead of linear. c) allows the sched_clock_cpu() value to warp the u64 without breaking. the results are more reliable sched_clock() deltas: before after sched_clock cpu_clock: 15750 51312 51488 cpu_clock: 59719 51052 50947 cpu_clock: 15879 51249 51061 cpu_clock: 1 50933 51198 cpu_clock: 1 50931 51039 cpu_clock: 1 51093 50981 cpu_clock: 1 51043 51040 cpu_clock: 1 50959 50938 cpu_clock: 1 50981 51011 cpu_clock: 1 51364 51212 cpu_clock: 1 51219 51273 cpu_clock: 1 51389 51048 cpu_clock: 1 51285 51611 cpu_clock: 1 50964 51137 cpu_clock: 1 50973 50968 cpu_clock: 1 50967 50972 cpu_clock: 1 58910 58485 cpu_clock: 1 51082 51025 cpu_clock: 1 50957 50958 cpu_clock: 1 50958 50957 cpu_clock: 1006128 51128 50971 cpu_clock: 1 51107 51155 cpu_clock: 1 51371 51081 cpu_clock: 1 51104 51365 cpu_clock: 1 51363 51309 cpu_clock: 1 51107 51160 cpu_clock: 1 51139 51100 cpu_clock: 1 51216 51136 cpu_clock: 1 51207 51215 cpu_clock: 1 51087 51263 cpu_clock: 1 51249 51177 cpu_clock: 1 51519 51412 cpu_clock: 1 51416 51255 cpu_clock: 1 51591 51594 cpu_clock: 1 50966 51374 cpu_clock: 1 50966 50966 cpu_clock: 1 51291 50948 cpu_clock: 1 50973 50867 cpu_clock: 1 50970 50970 cpu_clock: 998306 50970 50971 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 50971 50971 cpu_clock: 1 50970 50970 cpu_clock: 1 51351 50970 cpu_clock: 1 50970 51352 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 51321 50971 cpu_clock: 1 50974 51324 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-25 15:15:34 +00:00
if (unlikely(delta < 0))
delta = 0;
old_clock = scd->clock;
sched_clock: fix cpu_clock() This patch fixes 3 issues: a) it removes the dependency on jiffies, because jiffies are incremented by a single CPU, and the tick is not synchronized between CPUs. Therefore relying on it to calculate a window to clip whacky TSC values doesn't work as it can drift around. So instead use [GTOD, GTOD+TICK_NSEC) as the window. b) __update_sched_clock() did (roughly speaking): delta = sched_clock() - scd->tick_raw; clock += delta; Which gives exponential growth, instead of linear. c) allows the sched_clock_cpu() value to warp the u64 without breaking. the results are more reliable sched_clock() deltas: before after sched_clock cpu_clock: 15750 51312 51488 cpu_clock: 59719 51052 50947 cpu_clock: 15879 51249 51061 cpu_clock: 1 50933 51198 cpu_clock: 1 50931 51039 cpu_clock: 1 51093 50981 cpu_clock: 1 51043 51040 cpu_clock: 1 50959 50938 cpu_clock: 1 50981 51011 cpu_clock: 1 51364 51212 cpu_clock: 1 51219 51273 cpu_clock: 1 51389 51048 cpu_clock: 1 51285 51611 cpu_clock: 1 50964 51137 cpu_clock: 1 50973 50968 cpu_clock: 1 50967 50972 cpu_clock: 1 58910 58485 cpu_clock: 1 51082 51025 cpu_clock: 1 50957 50958 cpu_clock: 1 50958 50957 cpu_clock: 1006128 51128 50971 cpu_clock: 1 51107 51155 cpu_clock: 1 51371 51081 cpu_clock: 1 51104 51365 cpu_clock: 1 51363 51309 cpu_clock: 1 51107 51160 cpu_clock: 1 51139 51100 cpu_clock: 1 51216 51136 cpu_clock: 1 51207 51215 cpu_clock: 1 51087 51263 cpu_clock: 1 51249 51177 cpu_clock: 1 51519 51412 cpu_clock: 1 51416 51255 cpu_clock: 1 51591 51594 cpu_clock: 1 50966 51374 cpu_clock: 1 50966 50966 cpu_clock: 1 51291 50948 cpu_clock: 1 50973 50867 cpu_clock: 1 50970 50970 cpu_clock: 998306 50970 50971 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 50971 50971 cpu_clock: 1 50970 50970 cpu_clock: 1 51351 50970 cpu_clock: 1 50970 51352 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 51321 50971 cpu_clock: 1 50974 51324 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-25 15:15:34 +00:00
/*
* scd->clock = clamp(scd->tick_gtod + delta,
* max(scd->tick_gtod, scd->clock),
* scd->tick_gtod + TICK_NSEC);
sched_clock: fix cpu_clock() This patch fixes 3 issues: a) it removes the dependency on jiffies, because jiffies are incremented by a single CPU, and the tick is not synchronized between CPUs. Therefore relying on it to calculate a window to clip whacky TSC values doesn't work as it can drift around. So instead use [GTOD, GTOD+TICK_NSEC) as the window. b) __update_sched_clock() did (roughly speaking): delta = sched_clock() - scd->tick_raw; clock += delta; Which gives exponential growth, instead of linear. c) allows the sched_clock_cpu() value to warp the u64 without breaking. the results are more reliable sched_clock() deltas: before after sched_clock cpu_clock: 15750 51312 51488 cpu_clock: 59719 51052 50947 cpu_clock: 15879 51249 51061 cpu_clock: 1 50933 51198 cpu_clock: 1 50931 51039 cpu_clock: 1 51093 50981 cpu_clock: 1 51043 51040 cpu_clock: 1 50959 50938 cpu_clock: 1 50981 51011 cpu_clock: 1 51364 51212 cpu_clock: 1 51219 51273 cpu_clock: 1 51389 51048 cpu_clock: 1 51285 51611 cpu_clock: 1 50964 51137 cpu_clock: 1 50973 50968 cpu_clock: 1 50967 50972 cpu_clock: 1 58910 58485 cpu_clock: 1 51082 51025 cpu_clock: 1 50957 50958 cpu_clock: 1 50958 50957 cpu_clock: 1006128 51128 50971 cpu_clock: 1 51107 51155 cpu_clock: 1 51371 51081 cpu_clock: 1 51104 51365 cpu_clock: 1 51363 51309 cpu_clock: 1 51107 51160 cpu_clock: 1 51139 51100 cpu_clock: 1 51216 51136 cpu_clock: 1 51207 51215 cpu_clock: 1 51087 51263 cpu_clock: 1 51249 51177 cpu_clock: 1 51519 51412 cpu_clock: 1 51416 51255 cpu_clock: 1 51591 51594 cpu_clock: 1 50966 51374 cpu_clock: 1 50966 50966 cpu_clock: 1 51291 50948 cpu_clock: 1 50973 50867 cpu_clock: 1 50970 50970 cpu_clock: 998306 50970 50971 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 50971 50971 cpu_clock: 1 50970 50970 cpu_clock: 1 51351 50970 cpu_clock: 1 50970 51352 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 51321 50971 cpu_clock: 1 50974 51324 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-25 15:15:34 +00:00
*/
gtod = scd->tick_gtod + __gtod_offset;
clock = gtod + delta;
min_clock = wrap_max(gtod, old_clock);
max_clock = wrap_max(old_clock, gtod + TICK_NSEC);
sched_clock: fix cpu_clock() This patch fixes 3 issues: a) it removes the dependency on jiffies, because jiffies are incremented by a single CPU, and the tick is not synchronized between CPUs. Therefore relying on it to calculate a window to clip whacky TSC values doesn't work as it can drift around. So instead use [GTOD, GTOD+TICK_NSEC) as the window. b) __update_sched_clock() did (roughly speaking): delta = sched_clock() - scd->tick_raw; clock += delta; Which gives exponential growth, instead of linear. c) allows the sched_clock_cpu() value to warp the u64 without breaking. the results are more reliable sched_clock() deltas: before after sched_clock cpu_clock: 15750 51312 51488 cpu_clock: 59719 51052 50947 cpu_clock: 15879 51249 51061 cpu_clock: 1 50933 51198 cpu_clock: 1 50931 51039 cpu_clock: 1 51093 50981 cpu_clock: 1 51043 51040 cpu_clock: 1 50959 50938 cpu_clock: 1 50981 51011 cpu_clock: 1 51364 51212 cpu_clock: 1 51219 51273 cpu_clock: 1 51389 51048 cpu_clock: 1 51285 51611 cpu_clock: 1 50964 51137 cpu_clock: 1 50973 50968 cpu_clock: 1 50967 50972 cpu_clock: 1 58910 58485 cpu_clock: 1 51082 51025 cpu_clock: 1 50957 50958 cpu_clock: 1 50958 50957 cpu_clock: 1006128 51128 50971 cpu_clock: 1 51107 51155 cpu_clock: 1 51371 51081 cpu_clock: 1 51104 51365 cpu_clock: 1 51363 51309 cpu_clock: 1 51107 51160 cpu_clock: 1 51139 51100 cpu_clock: 1 51216 51136 cpu_clock: 1 51207 51215 cpu_clock: 1 51087 51263 cpu_clock: 1 51249 51177 cpu_clock: 1 51519 51412 cpu_clock: 1 51416 51255 cpu_clock: 1 51591 51594 cpu_clock: 1 50966 51374 cpu_clock: 1 50966 50966 cpu_clock: 1 51291 50948 cpu_clock: 1 50973 50867 cpu_clock: 1 50970 50970 cpu_clock: 998306 50970 50971 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 50971 50971 cpu_clock: 1 50970 50970 cpu_clock: 1 51351 50970 cpu_clock: 1 50970 51352 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 51321 50971 cpu_clock: 1 50974 51324 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-25 15:15:34 +00:00
clock = wrap_max(clock, min_clock);
clock = wrap_min(clock, max_clock);
if (cmpxchg64(&scd->clock, old_clock, clock) != old_clock)
goto again;
return clock;
}
static u64 sched_clock_remote(struct sched_clock_data *scd)
{
struct sched_clock_data *my_scd = this_scd();
u64 this_clock, remote_clock;
u64 *ptr, old_val, val;
sched_clock: Prevent 64bit inatomicity on 32bit systems The sched_clock_remote() implementation has the following inatomicity problem on 32bit systems when accessing the remote scd->clock, which is a 64bit value. CPU0 CPU1 sched_clock_local() sched_clock_remote(CPU0) ... remote_clock = scd[CPU0]->clock read_low32bit(scd[CPU0]->clock) cmpxchg64(scd->clock,...) read_high32bit(scd[CPU0]->clock) While the update of scd->clock is using an atomic64 mechanism, the readout on the remote cpu is not, which can cause completely bogus readouts. It is a quite rare problem, because it requires the update to hit the narrow race window between the low/high readout and the update must go across the 32bit boundary. The resulting misbehaviour is, that CPU1 will see the sched_clock on CPU1 ~4 seconds ahead of it's own and update CPU1s sched_clock value to this bogus timestamp. This stays that way due to the clamping implementation for about 4 seconds until the synchronization with CLOCK_MONOTONIC undoes the problem. The issue is hard to observe, because it might only result in a less accurate SCHED_OTHER timeslicing behaviour. To create observable damage on realtime scheduling classes, it is necessary that the bogus update of CPU1 sched_clock happens in the context of an realtime thread, which then gets charged 4 seconds of RT runtime, which results in the RT throttler mechanism to trigger and prevent scheduling of RT tasks for a little less than 4 seconds. So this is quite unlikely as well. The issue was quite hard to decode as the reproduction time is between 2 days and 3 weeks and intrusive tracing makes it less likely, but the following trace recorded with trace_clock=global, which uses sched_clock_local(), gave the final hint: <idle>-0 0d..30 400269.477150: hrtimer_cancel: hrtimer=0xf7061e80 <idle>-0 0d..30 400269.477151: hrtimer_start: hrtimer=0xf7061e80 ... irq/20-S-587 1d..32 400273.772118: sched_wakeup: comm= ... target_cpu=0 <idle>-0 0dN.30 400273.772118: hrtimer_cancel: hrtimer=0xf7061e80 What happens is that CPU0 goes idle and invokes sched_clock_idle_sleep_event() which invokes sched_clock_local() and CPU1 runs a remote wakeup for CPU0 at the same time, which invokes sched_remote_clock(). The time jump gets propagated to CPU0 via sched_remote_clock() and stays stale on both cores for ~4 seconds. There are only two other possibilities, which could cause a stale sched clock: 1) ktime_get() which reads out CLOCK_MONOTONIC returns a sporadic wrong value. 2) sched_clock() which reads the TSC returns a sporadic wrong value. #1 can be excluded because sched_clock would continue to increase for one jiffy and then go stale. #2 can be excluded because it would not make the clock jump forward. It would just result in a stale sched_clock for one jiffy. After quite some brain twisting and finding the same pattern on other traces, sched_clock_remote() remained the only place which could cause such a problem and as explained above it's indeed racy on 32bit systems. So while on 64bit systems the readout is atomic, we need to verify the remote readout on 32bit machines. We need to protect the local->clock readout in sched_clock_remote() on 32bit as well because an NMI could hit between the low and the high readout, call sched_clock_local() and modify local->clock. Thanks to Siegfried Wulsch for bearing with my debug requests and going through the tedious tasks of running a bunch of reproducer systems to generate the debug information which let me decode the issue. Reported-by: Siegfried Wulsch <Siegfried.Wulsch@rovema.de> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304051544160.21884@ionos Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: stable@vger.kernel.org
2013-04-06 08:10:27 +00:00
#if BITS_PER_LONG != 64
again:
/*
* Careful here: The local and the remote clock values need to
* be read out atomic as we need to compare the values and
* then update either the local or the remote side. So the
* cmpxchg64 below only protects one readout.
*
* We must reread via sched_clock_local() in the retry case on
* 32-bit kernels as an NMI could use sched_clock_local() via the
sched_clock: Prevent 64bit inatomicity on 32bit systems The sched_clock_remote() implementation has the following inatomicity problem on 32bit systems when accessing the remote scd->clock, which is a 64bit value. CPU0 CPU1 sched_clock_local() sched_clock_remote(CPU0) ... remote_clock = scd[CPU0]->clock read_low32bit(scd[CPU0]->clock) cmpxchg64(scd->clock,...) read_high32bit(scd[CPU0]->clock) While the update of scd->clock is using an atomic64 mechanism, the readout on the remote cpu is not, which can cause completely bogus readouts. It is a quite rare problem, because it requires the update to hit the narrow race window between the low/high readout and the update must go across the 32bit boundary. The resulting misbehaviour is, that CPU1 will see the sched_clock on CPU1 ~4 seconds ahead of it's own and update CPU1s sched_clock value to this bogus timestamp. This stays that way due to the clamping implementation for about 4 seconds until the synchronization with CLOCK_MONOTONIC undoes the problem. The issue is hard to observe, because it might only result in a less accurate SCHED_OTHER timeslicing behaviour. To create observable damage on realtime scheduling classes, it is necessary that the bogus update of CPU1 sched_clock happens in the context of an realtime thread, which then gets charged 4 seconds of RT runtime, which results in the RT throttler mechanism to trigger and prevent scheduling of RT tasks for a little less than 4 seconds. So this is quite unlikely as well. The issue was quite hard to decode as the reproduction time is between 2 days and 3 weeks and intrusive tracing makes it less likely, but the following trace recorded with trace_clock=global, which uses sched_clock_local(), gave the final hint: <idle>-0 0d..30 400269.477150: hrtimer_cancel: hrtimer=0xf7061e80 <idle>-0 0d..30 400269.477151: hrtimer_start: hrtimer=0xf7061e80 ... irq/20-S-587 1d..32 400273.772118: sched_wakeup: comm= ... target_cpu=0 <idle>-0 0dN.30 400273.772118: hrtimer_cancel: hrtimer=0xf7061e80 What happens is that CPU0 goes idle and invokes sched_clock_idle_sleep_event() which invokes sched_clock_local() and CPU1 runs a remote wakeup for CPU0 at the same time, which invokes sched_remote_clock(). The time jump gets propagated to CPU0 via sched_remote_clock() and stays stale on both cores for ~4 seconds. There are only two other possibilities, which could cause a stale sched clock: 1) ktime_get() which reads out CLOCK_MONOTONIC returns a sporadic wrong value. 2) sched_clock() which reads the TSC returns a sporadic wrong value. #1 can be excluded because sched_clock would continue to increase for one jiffy and then go stale. #2 can be excluded because it would not make the clock jump forward. It would just result in a stale sched_clock for one jiffy. After quite some brain twisting and finding the same pattern on other traces, sched_clock_remote() remained the only place which could cause such a problem and as explained above it's indeed racy on 32bit systems. So while on 64bit systems the readout is atomic, we need to verify the remote readout on 32bit machines. We need to protect the local->clock readout in sched_clock_remote() on 32bit as well because an NMI could hit between the low and the high readout, call sched_clock_local() and modify local->clock. Thanks to Siegfried Wulsch for bearing with my debug requests and going through the tedious tasks of running a bunch of reproducer systems to generate the debug information which let me decode the issue. Reported-by: Siegfried Wulsch <Siegfried.Wulsch@rovema.de> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304051544160.21884@ionos Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: stable@vger.kernel.org
2013-04-06 08:10:27 +00:00
* tracer and hit between the readout of
* the low 32-bit and the high 32-bit portion.
sched_clock: Prevent 64bit inatomicity on 32bit systems The sched_clock_remote() implementation has the following inatomicity problem on 32bit systems when accessing the remote scd->clock, which is a 64bit value. CPU0 CPU1 sched_clock_local() sched_clock_remote(CPU0) ... remote_clock = scd[CPU0]->clock read_low32bit(scd[CPU0]->clock) cmpxchg64(scd->clock,...) read_high32bit(scd[CPU0]->clock) While the update of scd->clock is using an atomic64 mechanism, the readout on the remote cpu is not, which can cause completely bogus readouts. It is a quite rare problem, because it requires the update to hit the narrow race window between the low/high readout and the update must go across the 32bit boundary. The resulting misbehaviour is, that CPU1 will see the sched_clock on CPU1 ~4 seconds ahead of it's own and update CPU1s sched_clock value to this bogus timestamp. This stays that way due to the clamping implementation for about 4 seconds until the synchronization with CLOCK_MONOTONIC undoes the problem. The issue is hard to observe, because it might only result in a less accurate SCHED_OTHER timeslicing behaviour. To create observable damage on realtime scheduling classes, it is necessary that the bogus update of CPU1 sched_clock happens in the context of an realtime thread, which then gets charged 4 seconds of RT runtime, which results in the RT throttler mechanism to trigger and prevent scheduling of RT tasks for a little less than 4 seconds. So this is quite unlikely as well. The issue was quite hard to decode as the reproduction time is between 2 days and 3 weeks and intrusive tracing makes it less likely, but the following trace recorded with trace_clock=global, which uses sched_clock_local(), gave the final hint: <idle>-0 0d..30 400269.477150: hrtimer_cancel: hrtimer=0xf7061e80 <idle>-0 0d..30 400269.477151: hrtimer_start: hrtimer=0xf7061e80 ... irq/20-S-587 1d..32 400273.772118: sched_wakeup: comm= ... target_cpu=0 <idle>-0 0dN.30 400273.772118: hrtimer_cancel: hrtimer=0xf7061e80 What happens is that CPU0 goes idle and invokes sched_clock_idle_sleep_event() which invokes sched_clock_local() and CPU1 runs a remote wakeup for CPU0 at the same time, which invokes sched_remote_clock(). The time jump gets propagated to CPU0 via sched_remote_clock() and stays stale on both cores for ~4 seconds. There are only two other possibilities, which could cause a stale sched clock: 1) ktime_get() which reads out CLOCK_MONOTONIC returns a sporadic wrong value. 2) sched_clock() which reads the TSC returns a sporadic wrong value. #1 can be excluded because sched_clock would continue to increase for one jiffy and then go stale. #2 can be excluded because it would not make the clock jump forward. It would just result in a stale sched_clock for one jiffy. After quite some brain twisting and finding the same pattern on other traces, sched_clock_remote() remained the only place which could cause such a problem and as explained above it's indeed racy on 32bit systems. So while on 64bit systems the readout is atomic, we need to verify the remote readout on 32bit machines. We need to protect the local->clock readout in sched_clock_remote() on 32bit as well because an NMI could hit between the low and the high readout, call sched_clock_local() and modify local->clock. Thanks to Siegfried Wulsch for bearing with my debug requests and going through the tedious tasks of running a bunch of reproducer systems to generate the debug information which let me decode the issue. Reported-by: Siegfried Wulsch <Siegfried.Wulsch@rovema.de> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304051544160.21884@ionos Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: stable@vger.kernel.org
2013-04-06 08:10:27 +00:00
*/
this_clock = sched_clock_local(my_scd);
/*
* We must enforce atomic readout on 32-bit, otherwise the
* update on the remote CPU can hit inbetween the readout of
* the low 32-bit and the high 32-bit portion.
sched_clock: Prevent 64bit inatomicity on 32bit systems The sched_clock_remote() implementation has the following inatomicity problem on 32bit systems when accessing the remote scd->clock, which is a 64bit value. CPU0 CPU1 sched_clock_local() sched_clock_remote(CPU0) ... remote_clock = scd[CPU0]->clock read_low32bit(scd[CPU0]->clock) cmpxchg64(scd->clock,...) read_high32bit(scd[CPU0]->clock) While the update of scd->clock is using an atomic64 mechanism, the readout on the remote cpu is not, which can cause completely bogus readouts. It is a quite rare problem, because it requires the update to hit the narrow race window between the low/high readout and the update must go across the 32bit boundary. The resulting misbehaviour is, that CPU1 will see the sched_clock on CPU1 ~4 seconds ahead of it's own and update CPU1s sched_clock value to this bogus timestamp. This stays that way due to the clamping implementation for about 4 seconds until the synchronization with CLOCK_MONOTONIC undoes the problem. The issue is hard to observe, because it might only result in a less accurate SCHED_OTHER timeslicing behaviour. To create observable damage on realtime scheduling classes, it is necessary that the bogus update of CPU1 sched_clock happens in the context of an realtime thread, which then gets charged 4 seconds of RT runtime, which results in the RT throttler mechanism to trigger and prevent scheduling of RT tasks for a little less than 4 seconds. So this is quite unlikely as well. The issue was quite hard to decode as the reproduction time is between 2 days and 3 weeks and intrusive tracing makes it less likely, but the following trace recorded with trace_clock=global, which uses sched_clock_local(), gave the final hint: <idle>-0 0d..30 400269.477150: hrtimer_cancel: hrtimer=0xf7061e80 <idle>-0 0d..30 400269.477151: hrtimer_start: hrtimer=0xf7061e80 ... irq/20-S-587 1d..32 400273.772118: sched_wakeup: comm= ... target_cpu=0 <idle>-0 0dN.30 400273.772118: hrtimer_cancel: hrtimer=0xf7061e80 What happens is that CPU0 goes idle and invokes sched_clock_idle_sleep_event() which invokes sched_clock_local() and CPU1 runs a remote wakeup for CPU0 at the same time, which invokes sched_remote_clock(). The time jump gets propagated to CPU0 via sched_remote_clock() and stays stale on both cores for ~4 seconds. There are only two other possibilities, which could cause a stale sched clock: 1) ktime_get() which reads out CLOCK_MONOTONIC returns a sporadic wrong value. 2) sched_clock() which reads the TSC returns a sporadic wrong value. #1 can be excluded because sched_clock would continue to increase for one jiffy and then go stale. #2 can be excluded because it would not make the clock jump forward. It would just result in a stale sched_clock for one jiffy. After quite some brain twisting and finding the same pattern on other traces, sched_clock_remote() remained the only place which could cause such a problem and as explained above it's indeed racy on 32bit systems. So while on 64bit systems the readout is atomic, we need to verify the remote readout on 32bit machines. We need to protect the local->clock readout in sched_clock_remote() on 32bit as well because an NMI could hit between the low and the high readout, call sched_clock_local() and modify local->clock. Thanks to Siegfried Wulsch for bearing with my debug requests and going through the tedious tasks of running a bunch of reproducer systems to generate the debug information which let me decode the issue. Reported-by: Siegfried Wulsch <Siegfried.Wulsch@rovema.de> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304051544160.21884@ionos Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: stable@vger.kernel.org
2013-04-06 08:10:27 +00:00
*/
remote_clock = cmpxchg64(&scd->clock, 0, 0);
#else
/*
* On 64-bit kernels the read of [my]scd->clock is atomic versus the
* update, so we can avoid the above 32-bit dance.
sched_clock: Prevent 64bit inatomicity on 32bit systems The sched_clock_remote() implementation has the following inatomicity problem on 32bit systems when accessing the remote scd->clock, which is a 64bit value. CPU0 CPU1 sched_clock_local() sched_clock_remote(CPU0) ... remote_clock = scd[CPU0]->clock read_low32bit(scd[CPU0]->clock) cmpxchg64(scd->clock,...) read_high32bit(scd[CPU0]->clock) While the update of scd->clock is using an atomic64 mechanism, the readout on the remote cpu is not, which can cause completely bogus readouts. It is a quite rare problem, because it requires the update to hit the narrow race window between the low/high readout and the update must go across the 32bit boundary. The resulting misbehaviour is, that CPU1 will see the sched_clock on CPU1 ~4 seconds ahead of it's own and update CPU1s sched_clock value to this bogus timestamp. This stays that way due to the clamping implementation for about 4 seconds until the synchronization with CLOCK_MONOTONIC undoes the problem. The issue is hard to observe, because it might only result in a less accurate SCHED_OTHER timeslicing behaviour. To create observable damage on realtime scheduling classes, it is necessary that the bogus update of CPU1 sched_clock happens in the context of an realtime thread, which then gets charged 4 seconds of RT runtime, which results in the RT throttler mechanism to trigger and prevent scheduling of RT tasks for a little less than 4 seconds. So this is quite unlikely as well. The issue was quite hard to decode as the reproduction time is between 2 days and 3 weeks and intrusive tracing makes it less likely, but the following trace recorded with trace_clock=global, which uses sched_clock_local(), gave the final hint: <idle>-0 0d..30 400269.477150: hrtimer_cancel: hrtimer=0xf7061e80 <idle>-0 0d..30 400269.477151: hrtimer_start: hrtimer=0xf7061e80 ... irq/20-S-587 1d..32 400273.772118: sched_wakeup: comm= ... target_cpu=0 <idle>-0 0dN.30 400273.772118: hrtimer_cancel: hrtimer=0xf7061e80 What happens is that CPU0 goes idle and invokes sched_clock_idle_sleep_event() which invokes sched_clock_local() and CPU1 runs a remote wakeup for CPU0 at the same time, which invokes sched_remote_clock(). The time jump gets propagated to CPU0 via sched_remote_clock() and stays stale on both cores for ~4 seconds. There are only two other possibilities, which could cause a stale sched clock: 1) ktime_get() which reads out CLOCK_MONOTONIC returns a sporadic wrong value. 2) sched_clock() which reads the TSC returns a sporadic wrong value. #1 can be excluded because sched_clock would continue to increase for one jiffy and then go stale. #2 can be excluded because it would not make the clock jump forward. It would just result in a stale sched_clock for one jiffy. After quite some brain twisting and finding the same pattern on other traces, sched_clock_remote() remained the only place which could cause such a problem and as explained above it's indeed racy on 32bit systems. So while on 64bit systems the readout is atomic, we need to verify the remote readout on 32bit machines. We need to protect the local->clock readout in sched_clock_remote() on 32bit as well because an NMI could hit between the low and the high readout, call sched_clock_local() and modify local->clock. Thanks to Siegfried Wulsch for bearing with my debug requests and going through the tedious tasks of running a bunch of reproducer systems to generate the debug information which let me decode the issue. Reported-by: Siegfried Wulsch <Siegfried.Wulsch@rovema.de> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304051544160.21884@ionos Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: stable@vger.kernel.org
2013-04-06 08:10:27 +00:00
*/
sched_clock_local(my_scd);
again:
this_clock = my_scd->clock;
remote_clock = scd->clock;
sched_clock: Prevent 64bit inatomicity on 32bit systems The sched_clock_remote() implementation has the following inatomicity problem on 32bit systems when accessing the remote scd->clock, which is a 64bit value. CPU0 CPU1 sched_clock_local() sched_clock_remote(CPU0) ... remote_clock = scd[CPU0]->clock read_low32bit(scd[CPU0]->clock) cmpxchg64(scd->clock,...) read_high32bit(scd[CPU0]->clock) While the update of scd->clock is using an atomic64 mechanism, the readout on the remote cpu is not, which can cause completely bogus readouts. It is a quite rare problem, because it requires the update to hit the narrow race window between the low/high readout and the update must go across the 32bit boundary. The resulting misbehaviour is, that CPU1 will see the sched_clock on CPU1 ~4 seconds ahead of it's own and update CPU1s sched_clock value to this bogus timestamp. This stays that way due to the clamping implementation for about 4 seconds until the synchronization with CLOCK_MONOTONIC undoes the problem. The issue is hard to observe, because it might only result in a less accurate SCHED_OTHER timeslicing behaviour. To create observable damage on realtime scheduling classes, it is necessary that the bogus update of CPU1 sched_clock happens in the context of an realtime thread, which then gets charged 4 seconds of RT runtime, which results in the RT throttler mechanism to trigger and prevent scheduling of RT tasks for a little less than 4 seconds. So this is quite unlikely as well. The issue was quite hard to decode as the reproduction time is between 2 days and 3 weeks and intrusive tracing makes it less likely, but the following trace recorded with trace_clock=global, which uses sched_clock_local(), gave the final hint: <idle>-0 0d..30 400269.477150: hrtimer_cancel: hrtimer=0xf7061e80 <idle>-0 0d..30 400269.477151: hrtimer_start: hrtimer=0xf7061e80 ... irq/20-S-587 1d..32 400273.772118: sched_wakeup: comm= ... target_cpu=0 <idle>-0 0dN.30 400273.772118: hrtimer_cancel: hrtimer=0xf7061e80 What happens is that CPU0 goes idle and invokes sched_clock_idle_sleep_event() which invokes sched_clock_local() and CPU1 runs a remote wakeup for CPU0 at the same time, which invokes sched_remote_clock(). The time jump gets propagated to CPU0 via sched_remote_clock() and stays stale on both cores for ~4 seconds. There are only two other possibilities, which could cause a stale sched clock: 1) ktime_get() which reads out CLOCK_MONOTONIC returns a sporadic wrong value. 2) sched_clock() which reads the TSC returns a sporadic wrong value. #1 can be excluded because sched_clock would continue to increase for one jiffy and then go stale. #2 can be excluded because it would not make the clock jump forward. It would just result in a stale sched_clock for one jiffy. After quite some brain twisting and finding the same pattern on other traces, sched_clock_remote() remained the only place which could cause such a problem and as explained above it's indeed racy on 32bit systems. So while on 64bit systems the readout is atomic, we need to verify the remote readout on 32bit machines. We need to protect the local->clock readout in sched_clock_remote() on 32bit as well because an NMI could hit between the low and the high readout, call sched_clock_local() and modify local->clock. Thanks to Siegfried Wulsch for bearing with my debug requests and going through the tedious tasks of running a bunch of reproducer systems to generate the debug information which let me decode the issue. Reported-by: Siegfried Wulsch <Siegfried.Wulsch@rovema.de> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304051544160.21884@ionos Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: stable@vger.kernel.org
2013-04-06 08:10:27 +00:00
#endif
/*
* Use the opportunity that we have both locks
* taken to couple the two clocks: we take the
* larger time as the latest time for both
* runqueues. (this creates monotonic movement)
*/
if (likely((s64)(remote_clock - this_clock) < 0)) {
ptr = &scd->clock;
old_val = remote_clock;
val = this_clock;
} else {
/*
* Should be rare, but possible:
*/
ptr = &my_scd->clock;
old_val = this_clock;
val = remote_clock;
}
if (cmpxchg64(ptr, old_val, val) != old_val)
goto again;
return val;
}
/*
* Similar to cpu_clock(), but requires local IRQs to be disabled.
*
* See cpu_clock().
*/
u64 sched_clock_cpu(int cpu)
{
struct sched_clock_data *scd;
u64 clock;
if (sched_clock_stable())
return sched_clock() + __sched_clock_offset;
2019-11-27 08:37:28 +00:00
if (!static_branch_likely(&sched_clock_running))
return sched_clock();
preempt_disable_notrace();
scd = cpu_sdc(cpu);
if (cpu != smp_processor_id())
clock = sched_clock_remote(scd);
else
clock = sched_clock_local(scd);
preempt_enable_notrace();
return clock;
}
EXPORT_SYMBOL_GPL(sched_clock_cpu);
void sched_clock_tick(void)
{
struct sched_clock_data *scd;
if (sched_clock_stable())
return;
2019-11-27 08:37:28 +00:00
if (!static_branch_likely(&sched_clock_running))
return;
lockdep_assert_irqs_disabled();
scd = this_scd();
__scd_stamp(scd);
sched_clock_local(scd);
}
void sched_clock_tick_stable(void)
{
if (!sched_clock_stable())
return;
/*
* Called under watchdog_lock.
*
* The watchdog just found this TSC to (still) be stable, so now is a
* good moment to update our __gtod_offset. Because once we find the
* TSC to be unstable, any computation will be computing crap.
*/
local_irq_disable();
__sched_clock_gtod_offset();
local_irq_enable();
}
/*
* We are going deep-idle (irqs are disabled):
*/
void sched_clock_idle_sleep_event(void)
{
sched_clock_cpu(smp_processor_id());
}
EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
/*
* We just idled; resync with ktime.
*/
void sched_clock_idle_wakeup_event(void)
{
unsigned long flags;
if (sched_clock_stable())
return;
if (unlikely(timekeeping_suspended))
return;
local_irq_save(flags);
sched_clock: fix cpu_clock() This patch fixes 3 issues: a) it removes the dependency on jiffies, because jiffies are incremented by a single CPU, and the tick is not synchronized between CPUs. Therefore relying on it to calculate a window to clip whacky TSC values doesn't work as it can drift around. So instead use [GTOD, GTOD+TICK_NSEC) as the window. b) __update_sched_clock() did (roughly speaking): delta = sched_clock() - scd->tick_raw; clock += delta; Which gives exponential growth, instead of linear. c) allows the sched_clock_cpu() value to warp the u64 without breaking. the results are more reliable sched_clock() deltas: before after sched_clock cpu_clock: 15750 51312 51488 cpu_clock: 59719 51052 50947 cpu_clock: 15879 51249 51061 cpu_clock: 1 50933 51198 cpu_clock: 1 50931 51039 cpu_clock: 1 51093 50981 cpu_clock: 1 51043 51040 cpu_clock: 1 50959 50938 cpu_clock: 1 50981 51011 cpu_clock: 1 51364 51212 cpu_clock: 1 51219 51273 cpu_clock: 1 51389 51048 cpu_clock: 1 51285 51611 cpu_clock: 1 50964 51137 cpu_clock: 1 50973 50968 cpu_clock: 1 50967 50972 cpu_clock: 1 58910 58485 cpu_clock: 1 51082 51025 cpu_clock: 1 50957 50958 cpu_clock: 1 50958 50957 cpu_clock: 1006128 51128 50971 cpu_clock: 1 51107 51155 cpu_clock: 1 51371 51081 cpu_clock: 1 51104 51365 cpu_clock: 1 51363 51309 cpu_clock: 1 51107 51160 cpu_clock: 1 51139 51100 cpu_clock: 1 51216 51136 cpu_clock: 1 51207 51215 cpu_clock: 1 51087 51263 cpu_clock: 1 51249 51177 cpu_clock: 1 51519 51412 cpu_clock: 1 51416 51255 cpu_clock: 1 51591 51594 cpu_clock: 1 50966 51374 cpu_clock: 1 50966 50966 cpu_clock: 1 51291 50948 cpu_clock: 1 50973 50867 cpu_clock: 1 50970 50970 cpu_clock: 998306 50970 50971 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 50971 50971 cpu_clock: 1 50970 50970 cpu_clock: 1 51351 50970 cpu_clock: 1 50970 51352 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 51321 50971 cpu_clock: 1 50974 51324 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-25 15:15:34 +00:00
sched_clock_tick();
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
void __init sched_clock_init(void)
{
static_branch_inc(&sched_clock_running);
local_irq_disable();
generic_sched_clock_init();
local_irq_enable();
}
u64 sched_clock_cpu(int cpu)
{
2019-11-27 08:37:28 +00:00
if (!static_branch_likely(&sched_clock_running))
return 0;
return sched_clock();
}
sched: Fix cpu_clock() in NMIs, on !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK Relax stable-sched-clock architectures to not save/disable/restore hardirqs in cpu_clock(). The background is that I was trying to resolve a sparc64 perf issue when I discovered this problem. On sparc64 I implement pseudo NMIs by simply running the kernel at IRQ level 14 when local_irq_disable() is called, this allows performance counter events to still come in at IRQ level 15. This doesn't work if any code in an NMI handler does local_irq_save() or local_irq_disable() since the "disable" will kick us back to cpu IRQ level 14 thus letting NMIs back in and we recurse. The only path which that does that in the perf event IRQ handling path is the code supporting frequency based events. It uses cpu_clock(). cpu_clock() simply invokes sched_clock() with IRQs disabled. And that's a fundamental bug all on it's own, particularly for the HAVE_UNSTABLE_SCHED_CLOCK case. NMIs can thus get into the sched_clock() code interrupting the local IRQ disable code sections of it. Furthermore, for the not-HAVE_UNSTABLE_SCHED_CLOCK case, the IRQ disabling done by cpu_clock() is just pure overhead and completely unnecessary. So the core problem is that sched_clock() is not NMI safe, but we are invoking it from NMI contexts in the perf events code (via cpu_clock()). A less important issue is the overhead of IRQ disabling when it isn't necessary in cpu_clock(). CONFIG_HAVE_UNSTABLE_SCHED_CLOCK architectures are not affected by this patch. Signed-off-by: David S. Miller <davem@davemloft.net> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20091213.182502.215092085.davem@davemloft.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-14 02:25:02 +00:00
#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
/*
* Running clock - returns the time that has elapsed while a guest has been
* running.
* On a guest this value should be local_clock minus the time the guest was
* suspended by the hypervisor (for any reason).
* On bare metal this function should return the same as local_clock.
* Architectures and sub-architectures can override this.
*/
u64 __weak running_clock(void)
{
return local_clock();
}